Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2502.04598 · Results in Physics

Arbitrary state preparation in quantum harmonic oscillators using neural networks

Nicolás Parra-A., Vladimir Vargas-Calderón, Herbert Vinck-Posada

Published Jul 1, 2026• 0 citations
arXivHTMLPDF

Abstract

Preparing quantum states is a fundamental task in various quantum algorithms. In particular, state preparation in quantum harmonic oscillators (HOs) is crucial for the manipulation of qudits and the implementation of high-dimensional algorithms. In this work, we develop a general methodology for quantum state preparation in an HO coupled to an auxiliary qubit, guaranteeing that any target state is physically preparable. Both the qubit and the HO are driven by two lasers with time-dependent phase modulation. The modulation times and phase values are generated by a neural network whose input is the desired target state. In contrast to conventional quantum control approaches, this framework eliminates the need for per-instance optimization of the control protocol. Instead, the control parameters required to prepare an arbitrary quantum state of the HO are obtained directly from a single forward pass through the neural network. Specifically, we present results for preparing arbitrary qubit, qutrit, and qudit ( 𝑛 = 4 ) states in the HO, achieving average fidelities of 99.99%, 99.5%, and 98.9%, respectively, across random target states.

DOI
10.1016/j.rinp.2026.108721

Related papers

Preparing Schrödinger Cat States in a Microwave Cavity Using a Neural Network

Hector Hutin, Pavlo V. Bilous, Chengzhi Ye +8 more

Scaling up quantum computing devices requires solving ever more complex quantum control tasks. Machine learning has been proposed as a promising approach to tackle the resulting challenges. However, experimental implementations are still scarce. In this work, we demonstrate experimentally a neural-network-based preparation of Schrödinger cat states in a cavity coupled dispersively to a qubit. We show that it is possible to teach a neural network to output optimized control pulses for a whole family of quantum states. After being trained in simulations, the network takes a description of the target quantum state as input and rapidly produces the pulse shape for the experiment, without any need for time-consuming additional optimization or retraining for different states. Our experimental results demonstrate more generally how deep neural networks and transfer learning can produce efficient simultaneous solutions to a range of quantum control tasks, which will benefit not only state preparation but also parametrized quantum gates.

arXiv:2409.05557•PRX Quantum•Jan 31, 2025•17 citations

Quantum State Preparation via Neural Network Encoding in Quantum Machine Learning

Kevin W. Aoun, Florian J. Kiwit, Carlos A. Riofrío +4 more

A central challenge in quantum machine learning is the state preparation bottleneck that describes the prohibitive computational cost of loading high-dimensional classical data into a quantum state. Although amplitude encoding can represent $2^n$-dimensional data using only $n$ qubits in principle, preparing arbitrary states remains computationally expensive, typically requiring variational optimization of a parameterized quantum circuit for each individual data instance. In this work, we propose a method that avoids iterative optimization by training a classical neural network to map input data directly to the continuous parameters of a fixed quantum circuit. We demonstrate the generation of quantum image states with high fidelity on data not seen during training. Since all optimization is performed once during training, the resulting model encodes new inputs in a single inference step, providing a scalable pathway for data loading in near-term quantum algorithms. We validate our method on the MNIST and Fashion-MNIST datasets, achieving fidelities up to 0.992 on unseen images and reducing the per-data-instance runtime by more than 5000-fold.

quant-pharXiv:2605.31006•Jun 1, 2026•0 citations

Classifying global state preparation via deep reinforcement learning

Tobias Haug, Wai-Keong Mok, Jia-Bin You +3 more

Abstract Quantum information processing often requires the preparation of arbitrary quantum states, such as all the states on the Bloch sphere for two-level systems. While numerical optimization can prepare individual target states, they lack the ability to find general control protocols that can generate many different target states. Here, we demonstrate global quantum control by preparing a continuous set of states with deep reinforcement learning. The protocols are represented using neural networks, which automatically groups the protocols into similar types, which could be useful for finding classes of protocols and extracting physical insights. As application, we generate arbitrary superposition states for the electron spin in complex multi-level nitrogen-vacancy centers, revealing classes of protocols characterized by specific preparation timescales. Our method could help improve control of near-term quantum computers, quantum sensing devices and quantum simulations.

arXiv:2005.12759•Machine Learning Science and Technology•Nov 5, 2020•37 citations

Arbitrary quantum states preparation aided by deep reinforcement learning

Zhaowei Wang, Zhao-Ming Wang

Abstract The preparation of quantum states is essential in the realm of quantum information processing, and the development of efficient methodologies can significantly alleviate the strain on quantum resources. Under the framework of deep reinforcement learning (DRL), we integrate the initial and the target state information within the state preparation task together, so as to realize the control trajectory design between two arbitrary quantum states. Taking a semiconductor double quantum dots (DQDs) model as an example, our results demonstrate that the resulting control trajectories can effectively achieve arbitrary quantum state preparation (AQSP) for both single-qubit and two-qubit systems, with average fidelities of 0.9868 and 0.9556 for the test sets, respectively. For the DQDs, charge and nuclear noises will exist, thus decreases the average fidelity of AQSP. We have also incorporated noise amplitude as an input feature in the training process, leading to the development of noise-aware models. The control trajectories designed by these models can effectively suppress the influence of noise. Our research validates the effectiveness of DRL in quantum state preparation and offers solutions for multi-initial and multi-objective quantum control tasks, with potential for broader application in quantum control problems.

arXiv:2407.16368•Physica Scripta•Feb 26, 2025•7 citations

Arbitrary-quantum-state preparation of a harmonic oscillator via optimal control

Katharina Rojan, Daniel M. Reich, I. Dotsenko +3 more

The efficient initialization of a quantum system is a prerequisite for quantum technological applications. Here we show that several classes of quantum states of a harmonic oscillator can be efficiently prepared by means of a Jaynes-Cummings interaction with a single two-level system. This is achieved by suitably tailoring external fields which drive the dipole and/or the oscillator. The time-dependent dynamics that leads to the target state is identified by means of optimal control theory (OCT) based on Krotov's method. Infidelities below ${10}^{\ensuremath{-}4}$ can be reached for the parameters of the experiment of Raimond, Haroche, Brune and co-workers, where the oscillator is a mode of a high-Q microwave cavity and the dipole is a Rydberg transition of an atom. For this specific situation we analyze the limitations on the fidelity due to parameter fluctuations and identify robust dynamics based on pulses found using ensemble OCT. Our analysis can be extended to quantum-state preparation of continuous-variable systems in other platforms, such as trapped ions and circuit QED.

arXiv:1406.6572•Physical Review A•Aug 14, 2014•36 citations

Critical States Preparation With Deep Reinforcement Learning

Jia-Wen Yu, Yi-Ming Yu, Ke-Xiong Yan +4 more

The fast and efficient preparation of quantum critical states is a challenging yet crucial task for various quantum technologies. This difficulty is most particularly for systems near a quantum phase transition, where the closure of the energy gap fundamentally limits the timescale of adiabatic processes and thus precludes rapid state preparation. We propose a framework using deep reinforcement learning (DRL) to rapidly prepare quantum critical states, with broad extendibility to light-matter interaction systems. Specifically, a DRL agent optimizes a set of time-dependent control Hamiltonians to drive the system from an initial noncritical state to a target critical state within a finite time and over experimentally accessible parameter ranges. As a concrete application, we focus on the quantum Rabi model. The DRL-optimized time-dependent control Hamiltonian yield a final state with high-fidelity ($>0.999$) to the target critical state. The protocol can be readily extended to other quantum critical systems described by light-matter interaction models, such as quantum Dicke model. This investigation provides a powerful new framework for preparing and manipulating quantum critical states.

quant-pharXiv:2603.09135•Physical Review Research•Mar 11, 2026•1 citation
Preparing quantum states is a fundamental task in various quantum algorithms. In particular, state preparation in quantum harmonic oscillators (HOs) is crucial for the manipulation of qudits and the implementation of high-dimensional algorithms. In this work, we develop a general methodology for quantum state preparation in an HO coupled to an auxiliary qubit, guaranteeing that any target state is physically preparable. Both the qubit and the HO are driven by two lasers with time-dependent phase modulation. The modulation times and phase values are generated by a neural network whose input is the desired target state. In contrast to conventional quantum control approaches, this framework eliminates the need for per-instance optimization of the control protocol. Instead, the control parameters required to prepare an arbitrary quantum state of the HO are obtained directly from a single forward pass through the neural network. Specifically, we present results for preparing arbitrary qubit, qutrit, and qudit ( 𝑛 = 4 ) states in the HO, achieving average fidelities of 99.99%, 99.5%, and 98.9%, respectively, across random target states.
Scaling up quantum computing devices requires solving ever more complex quantum control tasks. Machine learning has been proposed as a promising approach to tackle the resulting challenges. However, experimental implementations are still scarce. In this work, we demonstrate experimentally a neural-network-based preparation of Schrödinger cat states in a cavity coupled dispersively to a qubit. We show that it is possible to teach a neural network to output optimized control pulses for a whole family of quantum states. After being trained in simulations, the network takes a description of the target quantum state as input and rapidly produces the pulse shape for the experiment, without any need for time-consuming additional optimization or retraining for different states. Our experimental results demonstrate more generally how deep neural networks and transfer learning can produce efficient simultaneous solutions to a range of quantum control tasks, which will benefit not only state preparation but also parametrized quantum gates.
A central challenge in quantum machine learning is the state preparation bottleneck that describes the prohibitive computational cost of loading high-dimensional classical data into a quantum state. Although amplitude encoding can represent 2n2^n2n-dimensional data using only nnn qubits in principle, preparing arbitrary states remains computationally expensive, typically requiring variational optimization of a parameterized quantum circuit for each individual data instance. In this work, we propose a method that avoids iterative optimization by training a classical neural network to map input data directly to the continuous parameters of a fixed quantum circuit. We demonstrate the generation of quantum image states with high fidelity on data not seen during training. Since all optimization is performed once during training, the resulting model encodes new inputs in a single inference step, providing a scalable pathway for data loading in near-term quantum algorithms. We validate our method on the MNIST and Fashion-MNIST datasets, achieving fidelities up to 0.992 on unseen images and reducing the per-data-instance runtime by more than 5000-fold.
Abstract Quantum information processing often requires the preparation of arbitrary quantum states, such as all the states on the Bloch sphere for two-level systems. While numerical optimization can prepare individual target states, they lack the ability to find general control protocols that can generate many different target states. Here, we demonstrate global quantum control by preparing a continuous set of states with deep reinforcement learning. The protocols are represented using neural networks, which automatically groups the protocols into similar types, which could be useful for finding classes of protocols and extracting physical insights. As application, we generate arbitrary superposition states for the electron spin in complex multi-level nitrogen-vacancy centers, revealing classes of protocols characterized by specific preparation timescales. Our method could help improve control of near-term quantum computers, quantum sensing devices and quantum simulations.
Abstract The preparation of quantum states is essential in the realm of quantum information processing, and the development of efficient methodologies can significantly alleviate the strain on quantum resources. Under the framework of deep reinforcement learning (DRL), we integrate the initial and the target state information within the state preparation task together, so as to realize the control trajectory design between two arbitrary quantum states. Taking a semiconductor double quantum dots (DQDs) model as an example, our results demonstrate that the resulting control trajectories can effectively achieve arbitrary quantum state preparation (AQSP) for both single-qubit and two-qubit systems, with average fidelities of 0.9868 and 0.9556 for the test sets, respectively. For the DQDs, charge and nuclear noises will exist, thus decreases the average fidelity of AQSP. We have also incorporated noise amplitude as an input feature in the training process, leading to the development of noise-aware models. The control trajectories designed by these models can effectively suppress the influence of noise. Our research validates the effectiveness of DRL in quantum state preparation and offers solutions for multi-initial and multi-objective quantum control tasks, with potential for broader application in quantum control problems.
The efficient initialization of a quantum system is a prerequisite for quantum technological applications. Here we show that several classes of quantum states of a harmonic oscillator can be efficiently prepared by means of a Jaynes-Cummings interaction with a single two-level system. This is achieved by suitably tailoring external fields which drive the dipole and/or the oscillator. The time-dependent dynamics that leads to the target state is identified by means of optimal control theory (OCT) based on Krotov's method. Infidelities below ${10}^{\ensuremath{-}4}$ can be reached for the parameters of the experiment of Raimond, Haroche, Brune and co-workers, where the oscillator is a mode of a high-Q microwave cavity and the dipole is a Rydberg transition of an atom. For this specific situation we analyze the limitations on the fidelity due to parameter fluctuations and identify robust dynamics based on pulses found using ensemble OCT. Our analysis can be extended to quantum-state preparation of continuous-variable systems in other platforms, such as trapped ions and circuit QED.
The fast and efficient preparation of quantum critical states is a challenging yet crucial task for various quantum technologies. This difficulty is most particularly for systems near a quantum phase transition, where the closure of the energy gap fundamentally limits the timescale of adiabatic processes and thus precludes rapid state preparation. We propose a framework using deep reinforcement learning (DRL) to rapidly prepare quantum critical states, with broad extendibility to light-matter interaction systems. Specifically, a DRL agent optimizes a set of time-dependent control Hamiltonians to drive the system from an initial noncritical state to a target critical state within a finite time and over experimentally accessible parameter ranges. As a concrete application, we focus on the quantum Rabi model. The DRL-optimized time-dependent control Hamiltonian yield a final state with high-fidelity (>0.999>0.999>0.999) to the target critical state. The protocol can be readily extended to other quantum critical systems described by light-matter interaction models, such as quantum Dicke model. This investigation provides a powerful new framework for preparing and manipulating quantum critical states.